File size: 3,496 Bytes
7ea7636
 
 
ff28ad2
98f80b2
ff28ad2
7ea7636
 
 
 
 
 
 
98f80b2
 
 
7ea7636
98f80b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3670dd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d556080
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff28ad2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7ea7636
 
 
98f80b2
7ea7636
 
98f80b2
7ea7636
 
 
 
 
 
 
ff28ad2
7ea7636
 
 
 
ff28ad2
7ea7636
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005628269672913108,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1256539345826217e-05,
      "eval_loss": NaN,
      "eval_runtime": 1424.1245,
      "eval_samples_per_second": 26.266,
      "eval_steps_per_second": 13.133,
      "step": 1
    },
    {
      "epoch": 5.628269672913108e-05,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00011256539345826216,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00011256539345826216,
      "eval_loss": NaN,
      "eval_runtime": 1430.726,
      "eval_samples_per_second": 26.145,
      "eval_steps_per_second": 13.072,
      "step": 10
    },
    {
      "epoch": 0.00016884809018739323,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00022513078691652433,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.00022513078691652433,
      "eval_loss": NaN,
      "eval_runtime": 1432.0472,
      "eval_samples_per_second": 26.121,
      "eval_steps_per_second": 13.06,
      "step": 20
    },
    {
      "epoch": 0.0002814134836456554,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.00033769618037478646,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.00033769618037478646,
      "eval_loss": NaN,
      "eval_runtime": 1425.6894,
      "eval_samples_per_second": 26.237,
      "eval_steps_per_second": 13.119,
      "step": 30
    },
    {
      "epoch": 0.00039397887710391756,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.00045026157383304866,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.00045026157383304866,
      "eval_loss": NaN,
      "eval_runtime": 1436.5135,
      "eval_samples_per_second": 26.039,
      "eval_steps_per_second": 13.02,
      "step": 40
    },
    {
      "epoch": 0.0005065442705621797,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0005628269672913108,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0005628269672913108,
      "eval_loss": NaN,
      "eval_runtime": 1425.2675,
      "eval_samples_per_second": 26.245,
      "eval_steps_per_second": 13.122,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1621491292569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}